Nicola K Dinsdale

I am currently working as a post-doctoral research associate in the Oxford Machine Learning in NeuroImaging Lab (OMNI), working with Dr. Ana Namburete, in the Department of Computer Science. I studied for my DPhil (PhD) in the Analysis Group at the Wellcome Centre for Integrative Neuroimaging at the University of Oxford, where I researched deep learning based approaches for neuroimaging analysis, supervised by Prof. Mark Jenkinson and Dr. Ana Namburete, funded by the UKRI EPRSC/MRC as part of the ONBI DTC.

My research uses computer vision and deep learning to solve medical imaging problems. I am especially interested in exploring methods to overcome the barriers to clinical translatability of deep learning methods and robust deep learning, and I am open to collabortion opportunities.

Email  /  Google Scholar  /  Github

Recent Highlights

We propose UniFed, a unified federated harmonisation framework, which enables three key processes to be completed: 1) the training of a federated partially labelled harmonisation network, 2) the selection of the most appropriate pretrained model for a new unseen site, and 3) the incorporation of a new site into the harmonised federation.

Our model, TEDS-Net, generates anatomically plausible segmentations through deforming a prior shape with the same topology as the anatomy of interest.

We propose an uncertainty-aware deep learning model for automated 3D plane localization in 2D fetal brain images.

We investigated the performance of segmentation models trained on research data that were style-transferred to resemble clinical scans. Our results highlighted the importance of intensity normalisation methods in MRI segmentation, and their relation to domain shift and style-transfer.

Research Themes